INDEX

Explanations

for

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sonian

-0.29

proper

-0.27

ropriate

-0.27

éĻĭ

-0.26

éļĲçº¦

-0.26

ç¾¡

-0.26

implicit

-0.25

å¤§æĸ¹

-0.25

 favoured

-0.25

rieve

-0.25

POSITIVE LOGITS

åģļèµ·

0.28

è¾Ī

0.27

 Turk

0.26

Ã¢m

0.25

ç½®äºİ

0.25

 afin

0.24

æĬ¬å¤´

0.24

iter

0.24

åł°

0.24

ä¼ļåĲĮ

0.24

Activations Density 0.015%

for

No Comments

No Known Activations